chatglm3-6b in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,014 ±7
Percentile 3 · #284 · provisional
People prefer / Solves tasks
1,000 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,014 [1,007–1,022] Percentile 3 · #284 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
972 ±5.90 | 972 ±6 | 35.0% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
953 ±10 | 991 ±9 | 29.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
954 ±8.97 | 990 ±8 | 15.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
962 ±13 | 1,001 ±12 | 6.2% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Coding 1,023 [1,003–1,043] Percentile 3 · #270 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
964 ±13 | 993 ±12 | 85.5% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Math 1,032 [1,014–1,051] Percentile 3 · #247 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
989 ±12 | 999 ±11 | 83.5% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Writing 1,009 [988–1,030] Percentile 3 · #261 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
970 ±12 | 989 ±12 | 90.7% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Language: English 985 [972–998] Percentile 3 · #265 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,003 ±6.48 | 969 ±7 | 93.0% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
History
The same in a table
| Model | 2026-10 |
|---|---|
| chatglm3-6b | 1,014 D |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.